Use when designing the exhibits for a MIS Quarterly manuscript — measurement/correlation and structural-model tables for behavioral IS, regression and robustness tables for…
Ask questions against Mission Control's codebase understanding. Use for architecture questions, where-is-this-handled, why-does-this-exist, and codebase Q&A grounded in the…
Use when designing space missions, computing launch windows, optimizing trajectories, analyzing payload constraints, or planning mission phases and contingencies.
Implement Mistral AI reference architecture with best-practice project layout. Use when designing new Mistral AI integrations, reviewing project structure, or establishing…
Run a Mixture of Experts (MoE) audit on any topic, plan, codebase, evidence archive, or process. Dynamically spawns specialized subagents with different critical lenses to…
Deep expertise in ML/CV model selection, training pipelines, and inference architecture. Use when designing machine learning systems, computer vision pipelines, or AI-powered…
Use when the user wants an implementation plan, architecture design, or multi-step ML pipeline — "build X", "implement X", "design X", "set up X
Coaches end-to-end ML system design interviews covering inference pipelines, recommendation systems, RAG, feature stores, and monitoring.
A Principal ML Engineer interviewer that simulates a FAANG-style ML system design interview covering the full lifecycle from data to production.
Use when designing end-to-end ML systems, choosing batch vs streaming inference, preventing training/serving skew, building data flywheels, or planning ML infrastructure scaling.
End-to-end ML system design for production. Use when designing ML pipelines, feature stores, model training infrastructure, or serving systems.
Guides and validates architecture-aware ports of PyTorch/Hugging Face models to Apple MLX, inspects existing local MLX projects, and plans evidence-gated optimizations for Apple…
Alfred SuperAgent의 필수 규칙을 정의합니다. November 2025 enterprise standard 기반. 3-Layer architecture, 4-Step workflow, Agent-first paradigm, Skill invocation rules, AskUserQuestio — from…
Alfred SuperAgent의 필수 규칙을 정의합니다. November 2025 enterprise standard 기반. 3-Layer architecture, 4-Step workflow, Agent-first paradigm, Skill invocation rules, AskUserQuestio — from…
Authoring CLAUDE.md Project Instructions. Design project-specific AI guidance, document workflows, define architecture patterns.
Strategic thinking framework integrating First Principles Analysis, Stanford Design Thinking, and MIT Systems Engineering for deeper problem-solving.
Electron 33+ desktop app development specialist covering Main/Renderer process architecture, IPC communication, auto-update, and packaging with Electron Forge.
Implements and trains LLMs using Lightning AI's LitGPT with 20+ pretrained architectures (Llama, Gemma, Phi, Qwen, Mistral).
State-space model with O(n) complexity vs Transformers' O(n²). 5× faster inference, million-token sequences, no KV cache. Selective SSM with hardware-aware design.
Educational GPT implementation in ~300 lines. Reproduces GPT-2 (124M) on OpenWebText. Clean, hackable code for learning transformers. By Andrej Karpathy.
RNN+Transformer hybrid with O(n) inference. Linear time, infinite context, no KV cache. Train like GPT (parallel), infer like RNN (sequential).
Provides PyTorch-native distributed LLM pretraining using torchtitan with 4D parallelism (FSDP2, TP, PP, CP).
Use when after a deep neural network model has completed training on LC-MS spectral peak classification data and you need to preserve the learned weights and architecture for…
Esposter model-delegation conventions — the main session does all thinking (specs, proposals, architecture, review); mechanical implementation is delegated to background subagents…
Use when you have a trained baseline GNN model with established hyperparameters (dropout rate, learning rate, epochs, optimizer settings) and want to evaluate whether alternative…
Shape source-backed model and diagram review artifacts for architecture, UML-style, C4, dependency, and workflow views.
Vet the concrete third-party model a study will be built on — this repository, this revision, this checkpoint — not the architecture family.
Train machine learning models end-to-end, covering data loading, preprocessing, architecture selection, training loops, validation, and checkpointing.
Use when architecture boundaries, integrations, ownership, containers, components, deployment, dependencies, or stakeholder communication need C4-style views tied to value…
Workflow for converting, modernizing, upgrading, or re-architecting code (e.g. C++→Java, monolith→microservices), etc.
Skill para diseñar, revisar y generar artefactos de arquitectura modular (capas, features, boundaries, paquetes, y estrategias de integración).
Practical guidance for Go package design with minimal public APIs, single-responsibility boundaries, stateless-first flow, one-way state transitions, and…
Apply modular synthesis principles to system design, workflow architecture, and conceptual frameworks.
Use when when you need to understand how a multi-instrument mass spectrometry platform (like mzmine) decides which processing module receives a given dataset based on its — from…
Modular architecture health assessor for Logseq Template Graph. Analyzes module balance, cohesion, size distribution, and dependencies.
Produce a comprehensive module-level code review report for a path or subsystem. Use when the user wants architecture, concurrency, memory, kernel, or API review of a module with…
Core architecture of MoFA Studio: plugin system, shell/app boundaries, state coordination, theme and dark mode, and timer/event lifecycles.
Analyze the evolution of money and finance from Mesopotamian grain accounting through coinage, bills of exchange, central banking, the gold standard, fiat currency, and modern…
Build a modular monolith with clean internal seams and split to services only on proven pressure. Use when starting a system or resisting premature microservice decomposition.
Monolith-local Diversio PR review harness for deep PR understanding, deterministic worktree reuse/bootstrap, persistent review context across passes, resolved-comment-aware…
Implements vertical scaling, database optimization, caching tiering, deployment patterns, CI/CD pipelines, and observability strategies for growing monolithic applications to…
Monolith Terrain — visualización 3D de terreno con Three.js y datos geoespaciales.
Incrementally extracting a service from a Rails monolith — the strangler fig pattern, dark-launching, dual-writes with reconciliation, the cutover, the rollback plan, schema-level…
Monolith is a CLI tool and Rust library that saves complete web pages as a single HTML file by embedding CSS, images, JavaScript, and fonts as data URLs.
Expert in monorepo architecture, build systems, and dependency management at scale. Masters Nx, Turborepo, Bazel, and Lerna for efficient multi-project development.
Architecture du monorepo Poplist (npm workspaces + Turborepo + types partagés via @poplist/shared). À utiliser quand l'utilisateur ajoute/modifie/déboggue les fichiers de…
Recursively initialize AGENTS.md in monorepo subdirectories with smart detection. Creates hierarchical agent context files with proper linking to root CLAUDE.md and parent…
Expert guidance for building production-ready tool-calling agents with Databricks Mosaic AI Agent Framework.
Use when working in a GitHub repository connected to Moxie Docs — read its living documentation, conventions, and architecture context over the Moxie Docs MCP server before…
找出架構摩擦與 deep module 候選，但不直接修改實作程式碼。 Use when: 使用者要架構回看、找重構候選、改善可測性、 或把實作中暴露的架構摩擦整理成 OpenSpec 候選。
Architecture de messaging IoT avec MQTT incluant brokers, topics, QoS, sécurité et patterns. Se déclenche avec "MQTT", "broker MQTT", "Mosquitto", "IoT messaging", "topic — from…
Use when training embeddings from multi-modal spectral data (peak information + metadata) where you need to ensure both contrastive discriminability AND reconstruction fidelity.
design step of mspec workflow — write design.md + design-rationale.md + architecture-overview.md, full Constitution Check
Use when designing or evaluating MuleSoft Anypoint Platform deployment topology, runtime model selection, API governance with API Manager, or Anypoint Exchange strategy.
Use when designing a unified multi-channel service strategy spanning phone (Service Cloud Voice), email (Email-to-Case), chat (Messaging for In-App/Web), social, and SMS with…
Decision framework and patterns for architecting applications across AWS, Azure, and GCP.
Design multi-cloud architectures using a decision framework to select and integrate services across AWS, Azure, and GCP.
Choose between active-passive and active-active multi-region architectures with eyes open to data, cost, and failover reality.
Use when designing a strategy for multiple Experience Cloud sites within one Salesforce org, selecting a domain and URL pattern, planning shared LWC component libraries, designing…
Multi-store Commerce architecture: shared catalog, localization, multi-currency, multi-language, and regional storefront design for B2B, D2C, and SFCC deployments.